unicode: only list first android row

[sheet.git] / chars.plp

diff --git a/chars.plp b/chars.plp
index b081ac2749567468c920a663f81b52ffafed1372..5b5065e1391ac9a4dce04bd2102d2dbea5022e1a 100644 (file)
--- a/chars.plp
+++ b/chars.plp
@@ -7,33 +7,21 @@ Html({
                unicode glyph char character reference common ipa symbol sign mark table digraph
        '],
        stylesheet => [qw'light dark mono circus red'],
-       data => [qw'unicode-table.inc.pl unicode-char.inc.pl'],
+       data => [qw( unicode-cover.inc.pl ttfsupport unicode-char.inc.pl )],
 });
 
-:>
-<h1>Character support</h1>
-
-<p>
-Selected characters from Unicode <a href="/unicode">preset</a>
-or <a href="/charset">range</a>.
-</p>
-
-<div>
-
-<:
 use 5.010;
 use Shiar_Sheet::FormatChar;
 my $glyphs = Shiar_Sheet::FormatChar->new;
 
 my %oslist = (
        win95   => [qw( arial ariuni verdana times )],  # microsoft
-       mac10   => [qw( )],  # apple
+       mac10   => [qw( lucida garamond )],  # apple
        android => [qw( droidsans )],  # google
        oss     => [qw( dvsans c2k unifont )],
 );
-my @ossel = qw( win95 oss android );
+my @ossel = qw( win95 mac10 oss android );
 
-my $tables = do 'unicode-table.inc.pl' or die $@ || $!;
 my (%font, @fontlist);
 for my $os (@ossel) {
        my $osfonts = $oslist{$os};
@@ -51,61 +39,65 @@ for my $os (@ossel) {
 
 # parse input
 
-my @chars;
-my @querydesc;
-
-my $query = $ENV{PATH_INFO} || $get{q} || 'ipa';
-for ($query) {
-       s{^/}{};
-       when (qr{^[a-z]+(?:/|\z)}) {
-               for (split / /) {
-                       push @querydesc, "preset group $_";
-                       my ($tablegroup, $tablename) = split m{/}, $_, 2;
-                       my @tables = $tablename ? $tables->{$tablegroup}->{$tablename}
-                                  : sort values %{ $tables->{$tablegroup} };
-                       for (@tables) {
-                               my $includerows;  # ignore rows before body row
-                               for (@{$_}) {
-                                       $includerows ||= m/^[.]/ or next;
-                                       next if /^[.-]/;
-                                       next if $_ eq '>' or $_ eq '=';
-                                       push @chars, $_;
-                               }
-                       }
-               }
-               when ('ipa') {
-                       @chars = grep { !m/[a-zA-Z]/ } @chars;
-               }
-       }
-       when (qr{[\d,;\s+-]+}) {
-               push @querydesc, "character codepoints $_";
-               for (map { split /[^\d-]/ } $_) {
-                       my ($charnum, $range) = split /-/, $_;
-                       push @chars, chr $_ for $charnum .. ($range // $charnum);
+my ($title, $parent) = ('Character overview');
+my $query = eval {
+       for ($ENV{PATH_INFO} || ()) {
+               s{^/}{};
+               return $_ if m{^[0-9 +-]+$};
+
+               my ($cat, $name) = split m{/}, $_, 2 or die "invalid query\n";
+               if (!$name) {
+                       ($cat, $name) = ('table', $cat);
                }
+
+               my $groupinfo = do 'unicode-cover.inc.pl' or die $@ || $!;
+               my $row = $groupinfo->{$cat}->{$name}
+                       or die "unknown character group $cat/$name\n";
+
+               $title = ucfirst EscapeHTML($name).' characters';
+               $parent = $cat;
+               return EscapeHTML($row->{-query});
        }
-       when (qr{[A-Z]}) {
-               push @querydesc, "unicode match $_";
-               eval {
-                       my $match = qr/\A\p{$_}\z/;
-                       push @chars, grep { m/$match/ } map { chr $_ }
-                               0..0xD7FF, 0xE000..0xFDCF, 0xFDF0..0xFFFD;
-               } or die "invalid unicode match: $_\n";
-       }
-       default {
-               die "unknown parameter: $_\n";
-       }
+} || $get{q};
+
+say "<h1>$title</h1>";
+
+if (!$query) {
+       say "<p>Unicode group not specified: $@</p>";
+       exit;
+};
+
+for ($parent || 'Unicode range') {
+       my %CATDESC = (
+               block    => '<a href="/charset/unicode">Unicode block</a>',
+               script   => 'Unicode script',
+               category => 'Unicode category',
+               table    => '<a href="/unicode">Unicode preset group</a>',
+       );
+       say sprintf('<p>List %s in selected %s.</p>',
+               'characters and <a href="/font">font support</a>',
+               $CATDESC{$parent} || $parent,
+       );
 }
 
+my @chars;
+for (map { split /[^\d-]/ } $query) {
+       my @range = split /-/, $_, 2;
+       m/^[0-9]+$/ or die "Invalid code point $_ in query $query\n" for @range;
+       push @chars, chr $_ for $range[0] .. ($range[1] // $range[0]);
+}
+
+@chars or die "No match for query $query\n";
+
 @chars <= 1500 or die sprintf(
-       'too many matches (%d) for %s'."\n",
-       scalar @chars, join(', ', @querydesc),
+       'Too many matches (%d) for query %s'."\n",
+       scalar @chars, $query,
 );
 
 # output character list
 
+say '<div>';
 print '<table class=mapped>';
-say '<caption>'.EscapeHTML(join ', ', @querydesc).'</caption>';
 print '<col>' x 3;
 print "<colgroup span=$_>" for 2, map { scalar @{$oslist{$_}} } @ossel;
 
@@ -142,6 +134,5 @@ for my $chr (@chars) {
 }
 
 say "</table>\n";
-
-:></div>
+say "</div>\n";